9 citations · 20 across the 14 of their papers we have counts for
14 papers
Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
Pihe Hu, Shaolong Li, Zhuoran Li +2
Deep Multi-agent Reinforcement Learning (MARL) relies on neural networks with numerous parameters in multi-agent scenarios, often incurring substantial computational overhead. Cons…
Mixed Sparsity Training: Achieving 4 FLOP Reduction for Transformer Pretraining
Pihe Hu, Shaolong Li, Longbo Huang
Large language models (LLMs) have made significant strides in complex tasks, yet their widespread adoption is impeded by substantial computational demands. With hundreds of billion…
Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback
Yu Chen, Yihan Du, Pihe Hu +3
Risk-sensitive reinforcement learning (RL) aims to optimize policies that balance the expected reward and risk. In this paper, we present a novel risk-sensitive RL framework that e…
Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL
Zhuoran Li, Ling Pan, Jiatai Huang +1
We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on conserva…
Why (and When) does Local SGD Generalize Better than SGD?
Xinran Gu, Kaifeng Lyu, Longbo Huang +1
Local SGD is a communication-efficient variant of SGD for large-scale training, where multiple GPUs perform SGD independently and average the model parameters periodically. It has…
Queue Scheduling with Adversarial Bandit Learning
Jiatai Huang, Leana Golubchik, Longbo Huang
In this paper, we study scheduling of a queueing system with zero knowledge of instantaneous network conditions. We consider a one-hop single-server queueing system consisting of $…
RePreM: Representation Pre-training with Masked Model for Reinforcement Learning
Yuanying Cai, Chuheng Zhang, Wei Shen +3
Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Represent…
Stochastic Generative Flow Networks
Ling Pan, Dinghuai Zhang, Moksh Jain +2
Generative Flow Networks (or GFlowNets for short) are a family of probabilistic agents that learn to sample complex combinatorial structures through the lens of "inference as contr…
Provably Safe Reinforcement Learning with Step-wise Violation Constraints
Nuoya Xiong, Yihan Du, Longbo Huang
In this paper, we investigate a novel safe reinforcement learning problem with step-wise violation constraints. Our problem differs from existing works in that we consider stricter…
Multi-task Representation Learning for Pure Exploration in Linear Bandits
Yihan Du, Longbo Huang, Wen Sun
Despite the recent success of representation learning in sequential decision making, the study of the pure exploration scenario (i.e., identify the best option and minimize the sam…
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
Jiatai Huang, Yan Dai, Longbo Huang
We propose Banker Online Mirror Descent (Banker-OMD), a novel framework generalizing the classical Online Mirror Descent (OMD) technique in the online learning literature. The Bank…
Generative Augmented Flow Networks
Ling Pan, Dinghuai Zhang, Aaron Courville +2
The Generative Flow Network is a probabilistic framework where an agent learns a stochastic policy for object generation, such that the probability of generating an object is propo…
Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning
Pihe Hu, Ling Pan, Yu Chen +2
Multi-user delay constrained scheduling is important in many real-world applications including wireless communication, live streaming, and cloud computing. Yet, it poses a critical…
Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path
Yihan Du, Siwei Wang, Longbo Huang
In this paper, we study a novel episodic risk-sensitive Reinforcement Learning (RL) problem, named Iterated CVaR RL, which aims to maximize the tail of the reward-to-go at each ste…